© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 108848
    Prev
    Next
    INDEX
    Explanations

    temporal week references

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron activates on text describing shared weekly reading updates—phrases about what was read this past week and what one hopes to read in the coming week.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Years
    -1.07
    OfDay
    -0.99
     Years
    -0.96
    tahun
    -0.94
    years
    -0.93
     YEARS
    -0.91
     День
    -0.77
     Tages
    -0.77
    クイ
    -0.75
    Monthly
    -0.75
    POSITIVE LOGITS
     week
    6.53
     Week
    4.56
    week
    4.47
    Week
    4.31
     WEEK
    3.77
     semana
    3.61
    WEEK
    3.38
     weekly
    3.23
     semaine
    3.22
     weeks
    3.13
    Activations Density 0.138%

    No Known Activations